dptech-corp/Uni-Fold-jax
Trainable AlphaFold implementation in JAX
This project helps structural biologists and biochemists train their own deep learning models to predict protein structures. You provide amino acid sequences and known protein structures, and it outputs a customized model capable of predicting new protein structures from sequences. This is ideal for researchers who need specialized protein folding models beyond off-the-shelf solutions.
158 stars. No commits in the last 6 months.
Use this if you need to train a custom protein folding model from scratch using your own specialized datasets, or if you want to experiment with modifying the AlphaFold architecture.
Not ideal if you only need to predict the structure of a few proteins and prefer using an existing, pre-trained service without managing model training infrastructure.
Stars
158
Forks
48
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 06, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dptech-corp/Uni-Fold-jax"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
mxfold/mxfold2
MXfold2: RNA secondary structure prediction using deep learning with thermodynamic integration
kyegomez/Open-AF3
Implementation of Alpha Fold 3 from the paper: "Accurate structure prediction of biomolecular...
PaddlePaddle/PaddleHelix
Bio-Computing Platform Featuring Large-Scale Representation Learning and Multi-Task Deep...
mjendrusch/salad
protein structure generation with sparse all-atom denoising models
dptech-corp/Uni-Fold
An open-source platform for developing protein models beyond AlphaFold.